© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3332
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.65
     dipendenti
    -0.56
     peines
    -0.55
     seduta
    -0.55
    paksa
    -0.55
     lumineuse
    -0.54
     faibles
    -0.54
     tiroirs
    -0.54
     sèche
    -0.54
     vendus
    -0.53
    POSITIVE LOGITS
     Portail
    0.61
    Hauptartikel
    0.60
     AspNetCore
    0.58
     Ubicación
    0.58
    parsedMessage
    0.56
    Portale
    0.55
    inaison
    0.55
    opsida
    0.55
    Portail
    0.52
    ondale
    0.52
    Activations Density 0.000%

    No Known Activations